Bounds of optimal learning.
Belavkin, Roman V. ORCID: https://orcid.org/0000-0002-2356-1447
(2009)
Bounds of optimal learning.
In: 2009 IEEE International Symposium on Adaptive Dynamic Programming and Reinforcement Learning, March 30 – April 2, 2009, Sheraton Music City Hotel, Nashville, TN, USA.
.
[Conference or Workshop Item]
|
PDF
Download (167kB) | Preview |
Abstract
Learning is considered as a dynamic process described by a trajectory on a statistical manifold, and a topology is introduced defining trajectories continuous in information. The analysis generalises the application of Orlicz spaces in non-parametric information geometry to topological function spaces with asymmetric gauge functions (e.g. quasi-metric spaces defined in terms of KL divergence). Optimality conditions are formulated for dynamical constraints, and two main results are outlined: 1) Parametrisation of optimal learning trajectories from empirical constraints using generalised characteristic potentials; 2) A gradient theorem for the potentials defining optimal utility and information bounds of a learning system. These results not only generalise some known relations of statistical mechanics and variational methods in information theory, but also can be used for optimisation of the exploration-exploitation balance in online learning systems.
Item Type: | Conference or Workshop Item (Paper) |
---|---|
Research Areas: | A. > School of Science and Technology > Computer Science A. > School of Science and Technology > Computer Science > Artificial Intelligence group |
Item ID: | 3489 |
Useful Links: | |
Depositing User: | Dr Roman Belavkin |
Date Deposited: | 24 Mar 2010 14:08 |
Last Modified: | 30 Nov 2022 01:25 |
URI: | https://eprints.mdx.ac.uk/id/eprint/3489 |
Actions (login required)
![]() |
View Item |
Statistics
Additional statistics are available via IRStats2.